2 Copyright 2015 6WIND S.A.
4 Redistribution and use in source and binary forms, with or without
5 modification, are permitted provided that the following conditions
8 * Redistributions of source code must retain the above copyright
9 notice, this list of conditions and the following disclaimer.
10 * Redistributions in binary form must reproduce the above copyright
11 notice, this list of conditions and the following disclaimer in
12 the documentation and/or other materials provided with the
14 * Neither the name of 6WIND S.A. nor the names of its
15 contributors may be used to endorse or promote products derived
16 from this software without specific prior written permission.
18 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
21 A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
22 OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23 SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24 LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28 OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
33 The MLX5 poll mode driver library (**librte_pmd_mlx5**) provides support for
34 **Mellanox ConnectX-4** and **Mellanox ConnectX-4 Lx** families of
35 10/25/40/50/100 Gb/s adapters as well as their virtual functions (VF) in
38 Information and documentation about these adapters can be found on the
39 `Mellanox website <http://www.mellanox.com>`__. Help is also provided by the
40 `Mellanox community <http://community.mellanox.com/welcome>`__.
42 There is also a `section dedicated to this poll mode driver
43 <http://www.mellanox.com/page/products_dyn?product_family=209&mtag=pmd_for_dpdk>`__.
47 Due to external dependencies, this driver is disabled by default. It must
48 be enabled manually by setting ``CONFIG_RTE_LIBRTE_MLX5_PMD=y`` and
51 Implementation details
52 ----------------------
54 Besides its dependency on libibverbs (that implies libmlx5 and associated
55 kernel support), librte_pmd_mlx5 relies heavily on system calls for control
56 operations such as querying/updating the MTU and flow control parameters.
58 For security reasons and robustness, this driver only deals with virtual
59 memory addresses. The way resources allocations are handled by the kernel
60 combined with hardware specifications that allow it to handle virtual memory
61 addresses directly ensure that DPDK applications cannot access random
62 physical memory (or memory that does not belong to the current process).
64 This capability allows the PMD to coexist with kernel network interfaces
65 which remain functional, although they stop receiving unicast packets as
66 long as they share the same MAC address.
68 Enabling librte_pmd_mlx5 causes DPDK applications to be linked against
74 - Multiple TX and RX queues.
75 - Support for scattered TX and RX frames.
76 - IPv4, IPv6, TCPv4, TCPv6, UDPv4 and UDPv6 RSS on any number of queues.
77 - Several RSS hash keys, one for each flow type.
78 - Configurable RETA table.
79 - Support for multiple MAC addresses.
83 - RX CRC stripping configuration.
85 - Multicast promiscuous mode.
86 - Hardware checksum offloads.
87 - Flow director (RTE_FDIR_MODE_PERFECT and RTE_FDIR_MODE_PERFECT_MAC_VLAN).
88 - Secondary process TX is supported.
89 - KVM and VMware ESX SR-IOV modes are supported.
94 - Inner RSS for VXLAN frames is not supported yet.
95 - Port statistics through software counters only.
96 - Hardware checksum offloads for VXLAN inner header are not supported yet.
97 - Secondary process RX is not supported.
105 These options can be modified in the ``.config`` file.
107 - ``CONFIG_RTE_LIBRTE_MLX5_PMD`` (default **n**)
109 Toggle compilation of librte_pmd_mlx5 itself.
111 - ``CONFIG_RTE_LIBRTE_MLX5_DEBUG`` (default **n**)
113 Toggle debugging code and stricter compilation flags. Enabling this option
114 adds additional run-time checks and debugging messages at the cost of
117 - ``CONFIG_RTE_LIBRTE_MLX5_TX_MP_CACHE`` (default **8**)
119 Maximum number of cached memory pools (MPs) per TX queue. Each MP from
120 which buffers are to be transmitted must be associated to memory regions
121 (MRs). This is a slow operation that must be cached.
123 This value is always 1 for RX queues since they use a single MP.
125 Environment variables
126 ~~~~~~~~~~~~~~~~~~~~~
128 - ``MLX5_PMD_ENABLE_PADDING``
130 Enables HW packet padding in PCI bus transactions.
132 When packet size is cache aligned and CRC stripping is enabled, 4 fewer
133 bytes are written to the PCI bus. Enabling padding makes such packets
136 In cases where PCI bandwidth is the bottleneck, padding can improve
139 This is disabled by default since this can also decrease performance for
140 unaligned packet sizes.
142 Run-time configuration
143 ~~~~~~~~~~~~~~~~~~~~~~
145 - librte_pmd_mlx5 brings kernel network interfaces up during initialization
146 because it is affected by their state. Forcing them down prevents packets
149 - **ethtool** operations on related kernel interfaces also affect the PMD.
151 - ``rxq_cqe_comp_en`` parameter [int]
153 A nonzero value enables the compression of CQE on RX side. This feature
154 allows to save PCI bandwidth and improve performance at the cost of a
155 slightly higher CPU usage. Enabled by default.
160 This driver relies on external libraries and kernel drivers for resources
161 allocations and initialization. The following dependencies are not part of
162 DPDK and must be installed separately:
166 User space Verbs framework used by librte_pmd_mlx5. This library provides
167 a generic interface between the kernel and low-level user space drivers
170 It allows slow and privileged operations (context initialization, hardware
171 resources allocations) to be managed by the kernel and fast operations to
172 never leave user space.
176 Low-level user space driver library for Mellanox ConnectX-4 devices,
177 it is automatically loaded by libibverbs.
179 This library basically implements send/receive calls to the hardware
182 - **Kernel modules** (mlnx-ofed-kernel)
184 They provide the kernel-side Verbs API and low level device drivers that
185 manage actual hardware initialization and resources sharing with user
188 Unlike most other PMDs, these modules must remain loaded and bound to
191 - mlx5_core: hardware driver managing Mellanox ConnectX-4 devices and
192 related Ethernet kernel network devices.
193 - mlx5_ib: InifiniBand device driver.
194 - ib_uverbs: user space driver for Verbs (entry point for libibverbs).
196 - **Firmware update**
198 Mellanox OFED releases include firmware updates for ConnectX-4 adapters.
200 Because each release provides new features, these updates must be applied to
201 match the kernel modules and libraries they come with.
205 Both libraries are BSD and GPL licensed. Linux kernel modules are GPL
208 Currently supported by DPDK:
210 - Mellanox OFED **3.3-1.0.0.0**.
212 - Minimum firmware version:
214 - ConnectX-4: **12.16.1006**
215 - ConnectX-4 Lx: **14.16.1006**
217 Getting Mellanox OFED
218 ~~~~~~~~~~~~~~~~~~~~~
220 While these libraries and kernel modules are available on OpenFabrics
221 Alliance's `website <https://www.openfabrics.org/>`__ and provided by package
222 managers on most distributions, this PMD requires Ethernet extensions that
223 may not be supported at the moment (this is a work in progress).
226 <http://www.mellanox.com/page/products_dyn?product_family=26&mtag=linux>`__
227 includes the necessary support and should be used in the meantime. For DPDK,
228 only libibverbs, libmlx5, mlnx-ofed-kernel packages and firmware updates are
229 required from that distribution.
233 Several versions of Mellanox OFED are available. Installing the version
234 this DPDK release was developed and tested against is strongly
235 recommended. Please check the `prerequisites`_.
240 Compared to librte_pmd_mlx4 that implements a single RSS configuration per
241 port, librte_pmd_mlx5 supports per-protocol RSS configuration.
243 Since ``testpmd`` defaults to IP RSS mode and there is currently no
244 command-line parameter to enable additional protocols (UDP and TCP as well
245 as IP), the following commands must be entered from its CLI to get the same
246 behavior as librte_pmd_mlx4:
248 .. code-block:: console
251 > port config all rss all
257 This section demonstrates how to launch **testpmd** with Mellanox ConnectX-4
258 devices managed by librte_pmd_mlx5.
260 #. Load the kernel modules:
262 .. code-block:: console
264 modprobe -a ib_uverbs mlx5_core mlx5_ib
266 Alternatively if MLNX_OFED is fully installed, the following script can
269 .. code-block:: console
271 /etc/init.d/openibd restart
275 User space I/O kernel modules (uio and igb_uio) are not used and do
276 not have to be loaded.
278 #. Make sure Ethernet interfaces are in working order and linked to kernel
279 verbs. Related sysfs entries should be present:
281 .. code-block:: console
283 ls -d /sys/class/net/*/device/infiniband_verbs/uverbs* | cut -d / -f 5
287 .. code-block:: console
294 #. Optionally, retrieve their PCI bus addresses for whitelisting:
296 .. code-block:: console
299 for intf in eth2 eth3 eth4 eth5;
301 (cd "/sys/class/net/${intf}/device/" && pwd -P);
304 sed -n 's,.*/\(.*\),-w \1,p'
308 .. code-block:: console
315 #. Request huge pages:
317 .. code-block:: console
319 echo 1024 > /sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages/nr_hugepages
321 #. Start testpmd with basic parameters:
323 .. code-block:: console
325 testpmd -c 0xff00 -n 4 -w 05:00.0 -w 05:00.1 -w 06:00.0 -w 06:00.1 -- --rxq=2 --txq=2 -i
329 .. code-block:: console
332 EAL: PCI device 0000:05:00.0 on NUMA socket 0
333 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
334 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_0" (VF: false)
335 PMD: librte_pmd_mlx5: 1 port(s) detected
336 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:fe
337 EAL: PCI device 0000:05:00.1 on NUMA socket 0
338 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
339 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_1" (VF: false)
340 PMD: librte_pmd_mlx5: 1 port(s) detected
341 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:ff
342 EAL: PCI device 0000:06:00.0 on NUMA socket 0
343 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
344 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_2" (VF: false)
345 PMD: librte_pmd_mlx5: 1 port(s) detected
346 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:fa
347 EAL: PCI device 0000:06:00.1 on NUMA socket 0
348 EAL: probe driver: 15b3:1013 librte_pmd_mlx5
349 PMD: librte_pmd_mlx5: PCI information matches, using device "mlx5_3" (VF: false)
350 PMD: librte_pmd_mlx5: 1 port(s) detected
351 PMD: librte_pmd_mlx5: port 1 MAC address is e4:1d:2d:e7:0c:fb
352 Interactive-mode selected
353 Configuring Port 0 (socket 0)
354 PMD: librte_pmd_mlx5: 0x8cba80: TX queues number update: 0 -> 2
355 PMD: librte_pmd_mlx5: 0x8cba80: RX queues number update: 0 -> 2
356 Port 0: E4:1D:2D:E7:0C:FE
357 Configuring Port 1 (socket 0)
358 PMD: librte_pmd_mlx5: 0x8ccac8: TX queues number update: 0 -> 2
359 PMD: librte_pmd_mlx5: 0x8ccac8: RX queues number update: 0 -> 2
360 Port 1: E4:1D:2D:E7:0C:FF
361 Configuring Port 2 (socket 0)
362 PMD: librte_pmd_mlx5: 0x8cdb10: TX queues number update: 0 -> 2
363 PMD: librte_pmd_mlx5: 0x8cdb10: RX queues number update: 0 -> 2
364 Port 2: E4:1D:2D:E7:0C:FA
365 Configuring Port 3 (socket 0)
366 PMD: librte_pmd_mlx5: 0x8ceb58: TX queues number update: 0 -> 2
367 PMD: librte_pmd_mlx5: 0x8ceb58: RX queues number update: 0 -> 2
368 Port 3: E4:1D:2D:E7:0C:FB
369 Checking link statuses...
370 Port 0 Link Up - speed 40000 Mbps - full-duplex
371 Port 1 Link Up - speed 40000 Mbps - full-duplex
372 Port 2 Link Up - speed 10000 Mbps - full-duplex
373 Port 3 Link Up - speed 10000 Mbps - full-duplex